AI Models Leaderboard 2026

Compare the latest published AI model snapshot across pricing, context windows, latency, and benchmark performance.

Model	Intelligence	MMLU Pro	Context	GPQA	TTFT (s)	Speed (T/s)	Input Price (1M)	Output Price (1M)
Meta: Llama 3.2 3B Instruct Meta	-	-	80K	-	-	-	$0.05	$0.34
Meta: Llama 3.3 70B Instruct Meta	-	-	131K	-	-	-	$0.10	$0.32
Meta: Llama Guard 4 12B Meta	-	-	164K	-	-	-	$0.18	$0.18
Mi:dm K 2.5 Pro Preview Korea Telecom	-	81.3%	-	72.2%	-	-	$0.00	$0.00
MiniMax: MiniMax M1 MiniMax	-	-	1000K	-	-	-	$0.40	$2.20
MiniMax: MiniMax M2-her MiniMax	-	-	66K	-	-	-	$0.30	$1.20
MiniMax: MiniMax-01 MiniMax	-	-	1000K	-	-	-	$0.20	$1.10
Mistral Large 2411 mistralai	-	-	131K	-	-	-	$2.00	$6.00
Mistral: Codestral 2508 Mistral	-	-	256K	-	-	-	$0.30	$0.90
Mistral: Devstral 2 2512 Mistral	-	-	262K	-	-	-	$0.40	$2.00
Mistral: Ministral 3 14B 2512 Mistral	-	-	262K	-	-	-	$0.20	$0.20
Mistral: Ministral 3 3B 2512 Mistral	-	-	131K	-	-	-	$0.10	$0.10
Mistral: Ministral 3 8B 2512 Mistral	-	-	262K	-	-	-	$0.15	$0.15
Mistral: Mistral 7B Instruct v0.1 Mistral	-	-	3K	-	-	-	$0.11	$0.19
Mistral: Mistral Large 3 2512 Mistral	-	-	262K	-	-	-	$0.50	$1.50
Mistral: Mistral Nemo Mistral	-	-	131K	-	-	-	$0.01	$0.03
Mistral: Mistral Small 3.1 24B Mistral	-	-	128K	-	-	-	$0.35	$0.56
Mistral: Mistral Small 3.2 24B Mistral	-	-	128K	-	-	-	$0.07	$0.20
Mistral: Mistral Small Creative Mistral	-	-	33K	-	-	-	$0.10	$0.30
Mistral: Voxtral Small 24B 2507 Mistral	-	-	32K	-	-	-	$0.10	$0.30

Showing 561-580 of 667 models